Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1005
    Prev
    Next
    INDEX
    Explanations

    words related to migration, cultural differences, and struggles for employment

    oai_token-act-pair · gpt-3.5-turbo

    a specific punctuation mark that signifies emphasis or continuation in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •GPT2 L5 Resid: RRLLRLLRLLRRRRLLRRRRRRRRR

    No Comments

    Negative Logits
     dispers
    -0.77
     range
    -0.72
     confinement
    -0.72
     raft
    -0.72
     scattering
    -0.72
     scatter
    -0.71
     grips
    -0.70
     bonded
    -0.65
     relocation
    -0.65
     barrier
    -0.65
    POSITIVE LOGITS
    ¹
    1.08
    ĸļ
    1.05
    į
    1.04
    º
    1.02
    ¤
    0.99
    £
    0.99
    Į
    0.98
    ¡
    0.94
    »
    0.94
    ł
    0.93
    Activations Density 0.107%

    No Known Activations